Skip to content
2000
Volume 21, Issue 6
  • ISSN: 1573-4099
  • E-ISSN: 1875-6697

Abstract

Background

In recent years, analyzing complex biological networks to predict future links in such networks has attracted the attention of many medical and computer science researchers. The discovery of new drugs is one of the application cases for predicting future connections in biological networks. The operation of drug-target interactions prediction (DTIP) can be considered a fundamental step in identifying potential interactions between drug and target to identify new drugs.

Objective

The previous studies reveal that predictions are made based on known interactions using computational methods to solve the cost problem and avoid blind study of all interactions. But, there seem to be challenges such as the lack of confirmed negative samples and the low accuracy in some computational methods. Thus, we have proposed an efficient and hybrid approach called MKPUL-BLM to manage some of the aforementioned challenges for predicting drug-target interactions.

Methods

The MKPUL-BLM combins multi-kernel and positive unlabeled learning (PUL) approaches. Our method uses more information to increase accuracy, in addition to minimizing small similarities using network information. Also, potential negative samples are produced using a PUL approach because of lacking negative laboratory samples. Finally, labels are expanded a semi-supervised.

Results

Our method improved to 0.98 and 0.94 in the old interactions set for the ROCAUC and AUPR criteria, respectively. Also, this method enhanced ROCAUC and AUPR criteria by 0.89 and 0.77 for the new interactions set.

Conclusion

The MKPUL-BLM can be considered an efficient alternative to achieve more reliable predictions in the field of DTIP.

© 2025 Bentham Science Publishers
Loading

Article metrics loading...

/content/journals/cad/10.2174/0115734099288803240416103536
2024-04-19
2025-12-05

  • From This Site

    /content/journals/cad/10.2174/0115734099288803240416103536
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. PushpakomS. IorioF. EyersP.A. EscottK.J. HopperS. WellsA. DoigA. GuilliamsT. LatimerJ. McNameeC. NorrisA. SanseauP. CavallaD. PirmohamedM. Drug repurposing: Progress, challenges and recommendations.Nat. Rev. Drug Discov.2019181415810.1038/nrd.2018.168 30310233
     [Google Scholar]
  2. SachdevK. GuptaM.K. A comprehensive review of feature based methods for drug target interaction prediction.J. Biomed. Inform.20199310315910.1016/j.jbi.2019.103159 30926470
     [Google Scholar]
  3. ZhaoQ. YuH. JiM. ZhaoY. ChenX. Computational model development of drug-target interaction prediction: A review.Curr. Protein Pept. Sci.201920649249410.2174/1389203720666190123164310 30674253
     [Google Scholar]
  4. YaseenB.T. KurnazS. Drug–target interaction prediction using artificial intelligence.Appl. Nanosci.2021111
     [Google Scholar]
  5. BahiM. BatoucheM. Drug-target interaction prediction in drug repositioning based on deep semi-supervised learning.Comput. Intell. ApplChamSpringer201852230231310.1007/978‑3‑319‑89743‑1_27
     [Google Scholar]
  6. LiZ. HanP. YouZ-H. LiX. ZhangY. YuH. NieR. In silico prediction of drug-target interaction networks based on drug chemical structure and protein sequences.Sci. Rep.201771113 28127051
     [Google Scholar]
  7. YıldırımM.A. GohK.I. CusickM.E. BarabásiA.L. VidalM. Drug—target network.Nat. Biotechnol.200725101119112610.1038/nbt1338 17921997
     [Google Scholar]
  8. BagherianM. SabetiE. WangK. SartorM.A. Nikolovska-ColeskaZ. NajarianK. Machine learning approaches and databases for prediction of drug–target interaction: A survey paper.Brief. Bioinform.202122124726910.1093/bib/bbz157 31950972
     [Google Scholar]
  9. WangC. KurganL. Review and comparative assessment of similarity-based methods for prediction of drug–protein interactions in the druggable human proteome.Brief. Bioinform.20192062066208710.1093/bib/bby069 30102367
     [Google Scholar]
  10. LuY. GuoY. KorhonenA. Link prediction in drug-target interactions network using similarity indices.BMC Bioinformatics20171813910.1186/s12859‑017‑1460‑z 28095781
     [Google Scholar]
  11. BleakleyK. YamanishiY. Supervised prediction of drug–target interactions using bipartite local models.Bioinformatics200925182397240310.1093/bioinformatics/btp433 19605421
     [Google Scholar]
  12. van LaarhovenT. NabuursS.B. MarchioriE. Gaussian interaction profile kernels for predicting drug–target interaction.Bioinformatics201127213036304310.1093/bioinformatics/btr500 21893517
     [Google Scholar]
  13. XiaZ. WuL-Y. ZhouX. Semi-supervised drug-protein interaction prediction from heterogeneous biological spaces.BMC Syst. Biol.20104Suppl. 2S6
     [Google Scholar]
  14. KeumJ. NamH. SELF-BLM: Prediction of drug-target interactions via self-training SVM.PLoS One2017122e017183910.1371/journal.pone.0171839 28192537
     [Google Scholar]
  15. ÖztürkH. ÖzgürA. OzkirimliE. DeepDTA: Deep drug–target binding affinity prediction.Bioinformatics20183417i821i82910.1093/bioinformatics/bty593 30423097
     [Google Scholar]
  16. EzzatA. Challenges and solutions in drug-target interaction prediction.Doctoral thesis, Nanyang Technological University.: Singapore,2018
     [Google Scholar]
  17. HaddadiF. KayvanpourM.R. DTIP: A comparative analytical framework for chemogenomic drugtarget interactions prediction.Curr. Computeraided Drug Des.202117122110.2174/1573409916666191218124520 31854276
     [Google Scholar]
  18. ThomasM. BoardmanA. Garcia-OrtegonM. YangH. GraafC.d. Applications of Artificial Intelligence in Drug Design: Opportunities and Challenges.Artificial Intelligence in Drug Design2022159
     [Google Scholar]
  19. HaddadiF. PULBLM: A computational positive-unlabeled learning method for drug-target interactions prediction.10th Information and Knowledge Technology Conference (ICIKT2019)2020
     [Google Scholar]
  20. EzzatA. WuM. LiX.L. KwohC.K. Computational prediction of drug–target interactions using chemogenomic approaches: An empirical survey.Brief. Bioinform.20192041337135710.1093/bib/bby002 29377981
     [Google Scholar]
  21. GreenerJ.G. KandathilS.M. MoffatL. JonesD.T. A guide to machine learning for biologists.Nat. Rev. Mol. Cell Biol.2022231405510.1038/s41580‑021‑00407‑0 34518686
     [Google Scholar]
  22. DingY. TangJ. GuoF. Identification of drug-target interactions via multiple information integration.Inf. Sci.2017418-41954656010.1016/j.ins.2017.08.045
     [Google Scholar]
  23. DingY. TangJ. GuoF. Identification of drug–target interactions via fuzzy bipartite local model.Neural Comput. Appl.20203214103031031910.1007/s00521‑019‑04569‑z
     [Google Scholar]
  24. ZhengP. WangS. WangX. Artificial intelligence in bioinformatics and drug repurposing: Methods and applications.Front. Genet.202213870795
     [Google Scholar]
  25. KimH. KimE. LeeI. BaeB. ParkM. NamH. Artificial intelligence in drug discovery: A comprehensive review of data-driven and machine learning approaches.Biotechnol. Bioprocess Eng.; BBE202025689593010.1007/s12257‑020‑0049‑y 33437151
     [Google Scholar]
  26. SadeghiS.S. KeyvanpourM.R. An analytical review of computational drug repurposing.IEEE/ACM Trans. Comput. Biol. Bioinformatics202118247248810.1109/TCBB.2019.2933825 31403439
     [Google Scholar]
  27. SharifabadM.M. SheikhpourR. GharaghaniS. BRNS + SSFSM-DTI: A hybrid method for drug-target interaction prediction based on balanced reliable negative samples and semi-supervised feature selection.Chemom. Intell. Lab. Syst.202222010446210.1016/j.chemolab.2021.104462
     [Google Scholar]
  28. ChenR. LiuX. JinS. LinJ. LiuJ. Machine learning for drug-target interaction prediction.Molecules2018239220810.3390/molecules23092208 30200333
     [Google Scholar]
  29. RedkarS. MondalS. JosephA. HareeshaK.S. A machine learning approach for drug‐target interaction prediction using wrapper feature selection and class balancing.Mol. Inform.2020395190006210.1002/minf.201900062 32003548
     [Google Scholar]
  30. HaghaniS. KeyvanpourM.R. A systemic analysis of link prediction in social network.Artif. Intell. Rev.20195231961199510.1007/s10462‑017‑9590‑2
     [Google Scholar]
  31. KumarA. SinghS.S. SinghK. BiswasB. Link prediction techniques, applications, and performance: A survey.Physica A202055312428910.1016/j.physa.2020.124289
     [Google Scholar]
  32. a KolluriS. LinJ. LiuR. ZhangY. ZhangW. Machine learning and artificial intelligence in pharmaceutical research and development: A review.AAPS J.20222411910.1208/s12248‑021‑00644‑334984579
     [Google Scholar]
  33. b YouJ. IslamM. GrenierL. KuangQ. McLeodR.D. HuP. Drug-target interaction network predictions for drug repurposing using LASSO-based regularized linear classification model.Advances in Artificial IntelligenceChamSpringer20181083227227810.1007/978‑3‑319‑89656‑4_26
     [Google Scholar]
  34. JiangJ. WangN. ChenP. ZhangJ. DrugECs: An ensemble system with feature subspaces for accurate drug-target interaction prediction.Biomed Res. Int.201720176340316
     [Google Scholar]
  35. AbbasiK. RazzaghiP. PosoA. Ghanbari-AraS. Masoudi-NejadA. Deep learning in drug target interaction prediction: current and future perspectives.Curr. Med. Chem.202128112100211310.2174/1875533XMTA5qNzU62 32895036
     [Google Scholar]
  36. JunejoA.R. LiX. MadihaH. MohamedS. RETRACTED ARTICLE: Molecular communication networks: Drug target scalability based on artificial intelligence prediction techniques.J. Nanopart. Res.20212337510.1007/s11051‑021‑05181‑w
     [Google Scholar]
  37. van EngelenJ.E. HoosH.H. A survey on semi-supervised learning.Mach. Learn.2020109237344010.1007/s10994‑019‑05855‑6
     [Google Scholar]
  38. YamanishiY. ArakiM. GutteridgeA. HondaW. KanehisaM. Prediction of drug–target interaction networks from the integration of chemical and genomic spaces.Bioinformatics20082413i232i24010.1093/bioinformatics/btn162 18586719
     [Google Scholar]
  39. KanehisaM. GotoS. HattoriM. Aoki-KinoshitaK.F. ItohM. KawashimaS. KatayamaT. ArakiM. HirakawaM. From genomics to chemical genomics: New developments in KEGG.Nucleic Acids Res.20063490001Suppl. 1D354D35710.1093/nar/gkj102 16381885
     [Google Scholar]
  40. SchomburgI. ChangA. EbelingC. GremseM. HeldtC. HuhnG. SchomburgD. BRENDA, the enzyme database: Updates and major new developments.Nucleic Acids Res.20043290001Suppl. 1431D43310.1093/nar/gkh081 14681450
     [Google Scholar]
  41. GüntherS. KuhnM. DunkelM. CampillosM. SengerC. PetsalakiE. AhmedJ. UrdialesE.G. GewiessA. JensenL.J. SchneiderR. SkobloR. RussellR.B. BourneP.E. BorkP. PreissnerR. Supertarget and matador: Resources for exploring drug-target relationships.Nucleic Acids Res.200836Database issueSuppl. 1D919D922 17942422
     [Google Scholar]
  42. LawV. KnoxC. DjoumbouY. JewisonT. GuoA.C. LiuY. MaciejewskiA. ArndtD. WilsonM. NeveuV. TangA. GabrielG. LyC. AdamjeeS. DameZ.T. HanB. ZhouY. WishartD.S. DrugBank 4.0: Shedding new light on drug metabolism.Nucleic Acids Res.201442D1D1091D109710.1093/nar/gkt1068 24203711
     [Google Scholar]
  43. SmithT.F. WatermanM.S. Identification of common molecular subsequences.J. Mol. Biol.1981147119519710.1016/0022‑2836(81)90087‑5 7265238
     [Google Scholar]
  44. NascimentoA.C.A. PrudêncioR.B.C. CostaI.G. A multiple kernel learning algorithm for drug-target interaction prediction.BMC Bioinformatics20161714610.1186/s12859‑016‑0890‑3 26801218
     [Google Scholar]
  45. KlambauerG. WischenbartM. MahrM. UnterthinerT. MayrA. HochreiterS. Rchemcpp: A web service for structural analoging in ChEMBL, Drugbank and the Connectivity Map.Bioinformatics201531203392339410.1093/bioinformatics/btv373 26088801
     [Google Scholar]
  46. SmedleyD. HaiderS. DurinckS. PandiniL. ProveroP. AllenJ. ArnaizO. AwedhM.H. BaldockR. BarbieraG. BardouP. BeckT. BlakeA. BonierbaleM. BrookesA.J. BucciG. BuettiI. BurgeS. CabauC. CarlsonJ.W. ChelalaC. ChrysostomouC. CittaroD. CollinO. CordovaR. CuttsR.J. DassiE. GenovaA.D. DjariA. EspositoA. EstrellaH. EyrasE. Fernandez-BanetJ. ForbesS. FreeR.C. FujisawaT. GadaletaE. Garcia-ManteigaJ.M. GoodsteinD. GrayK. Guerra-AssunçãoJ.A. HaggartyB. HanD.J. HanB.W. HarrisT. HarshbargerJ. HastingsR.K. HayesR.D. HoedeC. HuS. HuZ.L. HutchinsL. KanZ. KawajiH. KelietA. KerhornouA. KimS. KinsellaR. KloppC. KongL. LawsonD. LazarevicD. LeeJ.H. LetellierT. LiC.Y. LioP. LiuC.J. LuoJ. MaassA. MarietteJ. MaurelT. MerellaS. MohamedA.M. MoreewsF. NabihoudineI. NdegwaN. NoirotC. Perez-LlamasC. PrimigM. QuattroneA. QuesnevilleH. RambaldiD. ReecyJ. RibaM. RosanoffS. SaddiqA.A. SalasE. SallouO. ShepherdR. SimonR. SperlingL. SpoonerW. StainesD.M. SteinbachD. StoneK. StupkaE. TeagueJ.W. Dayem UllahA.Z. WangJ. WareD. Wong-ErasmusM. Youens-ClarkK. ZadissaA. ZhangS.J. KasprzykA. The BioMart community portal: An innovative alternative to large, centralized data repositories.Nucleic Acids Res.201543W1W589W59810.1093/nar/gkv350 25897122
     [Google Scholar]
  47. OvaskaK. LaaksoM. HautaniemiS. Fast gene ontology based clustering for microarray experiments.BioData Min.2008111110.1186/1756‑0381‑1‑11 19025591
     [Google Scholar]
  48. MehrmolaeiS. EPTs-TL: A two-level approach for efficient event prediction in healthcare.Artif. Intell. Med.202111110199910.1016/j.artmed.2020.101999 33461692
     [Google Scholar]
  49. El-BeheryH. AttiaA.F. El-FishawyN. TorkeyH. Efficient machine learning model for predicting drug-target interactions with case study for Covid-19.Comput. Biol. Chem.20219310753610.1016/j.compbiolchem.2021.107536 34271420
     [Google Scholar]
  50. RefaeilzadehP. TangL. Cross-validation.Encyclopedia of Database SystemsBoston, MA.Springer20095532538
     [Google Scholar]
  51. FuG. DingY. SealA. ChenB. SunY. BoltonE. Predicting drug target interactions using meta-path-based semantic network analysis.BMC Bioinformatics201617116010.1186/s12859‑016‑1005‑x 27071755
     [Google Scholar]
  52. LanW. WangJ. LiM. LiuJ. LiY. WuF.X. PanY. Predicting drug–target interaction using positive-unlabeled learning.Neurocomputing2016206505710.1016/j.neucom.2016.03.080
     [Google Scholar]
  53. PengL. ZhuW. LiaoB. DuanY. ChenM. ChenY. YangJ. Screening drug-target interactions with positive-unlabeled learning.Sci. Rep.201771808710.1038/s41598‑017‑08079‑7 28808275
     [Google Scholar]
  54. YanX.Y. ZhangS.W. HeC.R. Prediction of drug-target interaction by integrating diverse heterogeneous information source with multiple kernel learning and clustering methods.Comput. Biol. Chem.20197846046710.1016/j.compbiolchem.2018.11.028 30528728
     [Google Scholar]
  55. HuangK. XiaoC. GlassL.M. SunJ. MolTrans: Molecular interaction transformer for drug–target interaction prediction.Bioinformatics202137683083610.1093/bioinformatics/btaa880 33070179
     [Google Scholar]
  56. YouJ. McLeodR.D. HuP. Predicting drug-target interaction network using deep learning model.Comput. Biol. Chem.201980809010110.1016/j.compbiolchem.2019.03.016 30939415
     [Google Scholar]
  57. IliadisD. De BaetsB. PahikkalaT. WaegemanW. A comparison of embedding aggregation strategies in drug–target interaction prediction.BMC Bioinformatics2024251597010.1186/s12859‑024‑05684‑y 38321386
     [Google Scholar]
  58. QiuY. ChengF. Artificial intelligence for drug discovery and development in Alzheimer’s disease.Curr. Opin. Struct. Biol.20248510277610.1016/j.sbi.2024.102776 38335558
     [Google Scholar]
  59. WeiJ. LuL. ShenT. Predicting drug–protein interactions by preserving the graph information of multi source data.BMC Bioinformatics20242511010.1186/s12859‑023‑05620‑6 38177981
     [Google Scholar]
  60. AskrH. ElgeldawiE. Aboul EllaH. ElshaierY.A.M.M. GomaaM.M. HassanienA.E. Deep learning in drug discovery: An integrative review and future challenges.Artif. Intell. Rev.20235675975603710.1007/s10462‑022‑10306‑1 36415536
     [Google Scholar]
  61. VoT.H. NguyenN.T.K. LeN.Q.K. Improved prediction of drug-drug interactions using ensemble deep neural networks.Medicine in Drug Discovery.20231710014910.1016/j.medidd.2022.100149
     [Google Scholar]
  62. ÖzçelikR. van TilborgD. Jiménez-LunaJ. GrisoniF. Structure‐based drug discovery with deep learning**.ChemBioChem20232413e20220077610.1002/cbic.202200776 37014633
     [Google Scholar]
  63. HaubenM. Artificial intelligence and data mining for the pharmacovigilance of drug–drug interactions.Clin. Ther.202345211713310.1016/j.clinthera.2023.01.002 36732152
     [Google Scholar]
  64. IsertC. AtzK. SchneiderG. Structure-based drug design with geometric deep learning.Curr. Opin. Struct. Biol.20237910254810.1016/j.sbi.2023.102548 36842415
     [Google Scholar]
  65. D’SouzaS. PremaK.V. BalajiS. Machine learning models for drug–target interactions: Current knowledge and future directions.Drug Discov. Today202025474875610.1016/j.drudis.2020.03.003 32171918
     [Google Scholar]
  66. PengJ. LiJ. ShangX. A learning-based method for drug-target interaction prediction based on feature representation learning and deep neural network.BMC Bioinformatics202021S13Suppl. 1339410.1186/s12859‑020‑03677‑1 32938374
     [Google Scholar]
  67. FengY.H. ZhangS.W. ShiJ.Y. DPDDI: A deep predictor for drug-drug interactions.BMC Bioinformatics202021141910.1186/s12859‑020‑03724‑x 32972364
     [Google Scholar]
  68. DuB.X. QinY. JiangY.F. XuY. YiuS.M. YuH. ShiJ.Y. Compound–protein interaction prediction by deep learning: Databases, descriptors and models.Drug Discov.202227513501366
     [Google Scholar]
  69. DaraS. DhamercherlaS. JadavS.S. BabuC.H.M. AhsanM.J. Machine learning in drug discovery: A review.Artif. Intell. Rev.20225531947199910.1007/s10462‑021‑10058‑4 34393317
     [Google Scholar]
  70. JaradaT.N. RokneJ.G. AlhajjR. A review of computational drug repositioning: Strategies, approaches, opportunities, challenges, and directions.J. Cheminform.20201214610.1186/s13321‑020‑00450‑7 33431024
     [Google Scholar]
  71. HuS. ZhangC. ChenP. GuP. ZhangJ. WangB. Predicting drug-target interactions from drug structure and protein sequence using novel convolutional neural networks.BMC Bioinformatics201920S25Suppl. 2568910.1186/s12859‑019‑3263‑x 31874614
     [Google Scholar]
  72. BuzaK. PeskaL. Aladin: A new approach for drug–target interaction prediction.Machine Learning and Knowledge Discovery in Databases: European Conference Skopje, Macedonia,September 18–22, 2017.322337
     [Google Scholar]
  73. EzzatA. WuM. LiX.L. KwohC.K. Drug-target interaction prediction via class imbalance-aware ensemble learning.BMC Bioinformatics201617S19Suppl. 1950910.1186/s12859‑016‑1377‑y 28155697
     [Google Scholar]
  74. MajumdarS. NandiS.K. GhosalS. GhoshB. MallikW. RoyN.D. BiswasA. MukherjeeS. PalS. BhattacharyyaN. Deep learning-based potential ligand prediction framework for COVID-19 with drug–target interaction model.Cognit. Comput.202111310.1007/s12559‑021‑09840‑x 33552306
     [Google Scholar]
  75. PliakosK. VensC. Drug-target interaction prediction with tree-ensemble learning and output space reconstruction.BMC Bioinformatics20202114910.1186/s12859‑020‑3379‑z 32033537
     [Google Scholar]
  76. ShiJ.Y. LiJ.X. LuH.M. Predicting existing targets for new drugs base on strategies for missing interactions.BMC Bioinformatics201617S8Suppl. 828210.1186/s12859‑016‑1118‑2 27585458
     [Google Scholar]
/content/journals/cad/10.2174/0115734099288803240416103536
Loading
An Enhanced Computational Approach Using Multi-kernel Positive Unlabeled Learning for Predicting Drug-target Interactions
Curr. Computeraided Drug Des. 21, 766 (2025); https://doi.org/10.2174/0115734099288803240416103536
/content/journals/cad/10.2174/0115734099288803240416103536
/content/journals/cad/10.2174/0115734099288803240416103536
Loading

Data & Media loading...


  • Article Type:     Research Article
Keyword(s): AUPR; Drug-target interactions; multi-kernel; positive-unlabeled learning; predicting targets; ROCAUC

Most Cited Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error
Please enter a valid_number test